Real-Time Defect and Object Detection in Assembly Line: A Case for In-Line Quality Inspection

Identification of flawed assemblies and defective parts or products as early as possible is a daily struggle for manufacturing companies. With the ever-increasing complexity of assembly operations and manufacturing processes alongside the need for shorter cycle times and higher flexibility of productions, companies cannot afford to check for quality issues only at the end of the line. In-line quality inspection needs to be considered as a vital part of the process. This paper explores use of a real-time automated solution for detection of assembly defects through YOLOv8 (You Only Look Once) deep learning algorithm which is a class of convolutional neural networks (CNN). The use cases of the algorithm can be extended into detection of multiple objects within a single image to account for not only defects and missing parts in an assembly operation, but also quality assurance of the process both in manual and automatic cells. An analysis of YOLOv8 algorithm over an industrial case study for object detection shows the mean average precision (mAP) of the model on the test dataset and consequently its overall performance is extremely high. An implementation of this model would facilitate in-line quality inspection and streamline quality control tasks in complex assembly operations.